Real-time dialogue between experimenters and dreamers during REM sleep

Abstract

Dreams take us to a different reality, a hallucinatory world that feels as real as any waking experience. These often-bizarre episodes are emblematic of human sleep but have yet to be adequately explained. Retrospective dream reports are subject to distortion and forgetting, presenting a fundamental challenge for neuroscientific studies of dreaming. Here we show that individuals who are asleep and in the midst of a lucid dream (aware of the fact that they are currently dreaming) can perceive questions from an experimenter and provide answers using electrophysiological signals. We implemented our procedures for two-way communication during polysomnographically verified rapid-eye-movement (REM) sleep in 36 individuals. Some had minimal prior experience with lucid dreaming, others were frequent lucid dreamers, and one was a patient with narcolepsy who had frequent lucid dreams. During REM sleep, these individuals exhibited various capabilities, including performing veridical perceptual analysis of novel information, maintaining information in working memory, computing simple answers, and expressing volitional replies. Their responses included distinctive eye movements and selective facial muscle contractions, constituting correctly answered questions on 29 occasions across 6 of the individuals tested. These repeated observations of interactive dreaming, documented by four independent laboratory groups, demonstrate that phenomenological and cognitive characteristics of dreaming can be interrogated in real time. This relatively unexplored communication channel can enable a variety of practical applications and a new strategy for the empirical exploration of dreams.

Keywords: REM sleep; consciousness; dreams; interactive dreaming; lucid dream; sensory processing; sleep learning; sleep mentation; targeted memory reactivation; two-way communication.

Figure 1.. Overview of the experimental setting

IN (lower left) refers to methods whereby information was transmitted from experimenter to dreamer. OUT (lower right) refers to methods whereby information was transmitted from dreamer to experimenter. Examples of three dreams (color-coded for each input method) are illustrated below relevant excerpts from corresponding dream reports obtained following awakening.

Figure 2.. Interactive dreaming (USA group)

(A) Hypnogram showing that REM sleep began 68 min after sleep onset. The auditory cue to induce lucidity was presented two times (blue arrow), followed by a microarousal and then a longer REM period with lucidity signals (LRLRLR) given six times starting at 69 min. (B) The left panel shows a 5 s period of wake, corresponding to the gray arrow on the hypnogram. The right panel shows a 30 s REM segment, in which the last two lucidity signals (indicated by red asterisks) were followed by two instances of the spoken stimulus “8 minus 6” (vertical lines, and red arrow in A). Both times, the correct answer was produced with eye signals (2). Upon awakening, the participant reported dreaming about his favorite video game: “I was in a parking lot at night…then suddenly it was daytime and I was in the video game…. I thought, okay this is probably a dream. And then something weird…. I lost control of all my muscles. There was a roaring sound of blood rushing to my ears.” The experimenter asked him whether he remembered hearing any math problems, how many he answered, and what he answered. The subject reported, “I think I heard three [problems]…. I answered ‘2’ for all of them, but I don’t remember what the first one was. I just remember the last one was ‘8 minus 6.”’ (For further details on sleep monitoring and terminology, see Nir and Tononi, Appel et al., and Baird et al.)

Figure 3.. Interactive dreaming (German group)

The participant was stimulated during REM sleep with red and green LED light flashes to convey Morse-coded math problems. (A) Hypnogram of the night. (B) An awake period (left) and a period of interactive dreaming during REM sleep (right), corresponding to the times indicated by the gray and red arrows in (A), respectively. The question “4 minus 0” was presented, as shown in green. The resulting answer “4” produced by the dreamer was apparent in the EOG signals. Upon awakening, the participant recalled the problem almost correctly. Dream report: “A medical practice, maybe for physiotherapy. I was alone in the room and there was a large doctor’s couch in the middle of the room, shelves, sideboards. The couch was strange. The room seemed solid and steady, when the lights started flickering. I recognized this as the flashing signal [Morse code] from the outside (4 plus 0, ) and reported the answer ‘4’ with eye signals. I looked for a tool that could flash, and I found a round bowl full of water. The water flashed (like a fish tank light that one turns on and off). I again saw a signal, but was not able to identify it. The bowl broke because I accidentally let it fall while trying to decode the flashes. I left the room, trying to find something else that could flash, and went outside and looked up to the clouds. There was yellow sunlight and light gray clouds. I saw variations in the brightness, clouds drifting past quickly, but again, unfortunately, I could not decipher a flashing signal. It was too fast to decode, but I knew that these were math problems.”

Figure 4.. Interactive dreaming (French group)

(A) Hypnogram showing a daytime nap in a participant with narcolepsy. The red arrow indicates the beginning of a yes-no question period. Before sleep, the participant was instructed to contract zygomatic muscles twice to signal “YES” and corrugator muscles twice to signal “NO.” (B) Polysomnographic results documenting periods of wake (left) and REM sleep from the beginning of a yes-no question period (right). The first question was answered correctly (NO signal). The next question was answered, but the answer was judged as ambiguous. Three further questions were asked. In total, four of these five questions were answered; negligible facial EMG activity was observed after one question. Two answers were rated as correct and two as ambiguous. There was no facial EMG activity outside of the stimulation periods. The dream report upon waking was as follows: “In my dream, I was at a party and I heard you asking questions. I heard your voice as if you were a God. Your voice was coming from the outside, just like a narrator of a movie. I heard you asking whether I like chocolate, whether I was studying biology, and whether I speak Spanish. I wasn’t sure how to answer the last one, because I am not fluent in Spanish, but I have some notions. In the end, I decided to answer ‘NO’ and went back to the party.”

Figure 5.. Interactive dreaming (Dutch group)

(A) Hypnogram of the nap. The blue arrow indicates the third instance when auditory and visual cues for lucid-dream induction were administered. We administered 24 math problems but refrained from immediately awakening this participant for a dream report due to highly fragmented REM sleep, with many stage N1 intrusions and movement arousals (indicated by red at bottom). (B) A period of wake with an LRLRLR signal (left, gray arrow in A) and a period of REM (right, red arrow in A). The math problem in this example (1 plus 2) was the seventh problem delivered and was followed by a correct eye-movement response (3). Dream report: “…in my dream I thought ‘I have to remember things’ and I heard the sounds and heard you talking while I was dreaming. I sat down in the car, and then I got a part of the assignment…. I was also really proud that I succeeded with a sum calculation, and that I heard them, and that I was aware that I was dreaming.” The participant stated that the source of the math problems “felt like a sort of radio in the car.”